© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10385
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to specific domains, such as computing, typography, chemistry, or fandom

    oai_token-act-pair · gemini-2.0-flash

    words with 's' and 'f' sounds

    np_token-act-pair-logits · gpt-4o-mini

    Technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.98
    æa
    -0.98
    ficult
    -0.97
     L
    -0.95
     G
    -0.93
     
    -0.93
     K
    -0.93
     T
    -0.91
    polation
    -0.91
     (
    -0.88
    POSITIVE LOGITS
     itſelf
    1.78
     Theſe
    1.66
     myſelf
    1.66
     Monfieur
    1.60
     Anſ
    1.57
     Reſ
    1.52
    ſelf
    1.48
     ſche
    1.48
     raiſ
    1.47
     purpoſe
    1.46
    Activations Density 16.668%

    No Known Activations